Update README.md

README.md

@@ -4,4 +4,8 @@ datasets:
 base_model:
 - unsloth/Llama-3.2-1B-Instruct
 ---
-Trained with tokenizer of [OpenRLHF/Llama-3-8b-sft-mixture](https://huggingface.co/OpenRLHF/Llama-3-8b-sft-mixture).
+Base mode: [unsloth/Llama-3.2-1B-Instruct](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct)
+
+Tokenizer: [OpenRLHF/Llama-3-8b-sft-mixture](https://huggingface.co/OpenRLHF/Llama-3-8b-sft-mixture)
+
+Preference dataset: [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)